Adaptive Mapping of Sound Collections for Data-driven Musical Interfaces

Gerard Roma, Owen Green, Pierre Alexandre Tremblay

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Citations (Scopus)


Descriptor spaces have become an ubiquitous interaction paradigm for music based on collections of audio samples. However, most systems rely on a small predefined set of descriptors, which the user is often required to understand
and choose from. There is no guarantee that the chosen descriptors are relevant for a given collection. In addition,this method does not scale to longer samples that require higher-dimensional descriptions, which biases systems towards the use of short samples. In this paper we propose novel framework for automatic creation of interactive sound spaces from sound collections using feature learning and dimensionality reduction. The framework is implemented as a
software library using the SuperCollider language. We compare several algorithms and describe some example interfaces for interacting with the resulting spaces. Our experiments signal the potential of unsupervised algorithms for creating data-driven musical interfaces.
Original languageEnglish
Title of host publicationProceedings of the International Conference on New Interfaces for Musical Expression
EditorsMarcelo Queiroz, Anna Xambó Sedó
Place of PublicationPorto Alegre
Number of pages6
Publication statusPublished - Jun 2019
19th International conference on New Interfaces for Musical Expression
- Porto Alegre, Brazil
Duration: 3 Jun 20196 Jun 2019

Publication series

NameProceedings of the conference on New Interface for Musical Expression (NIME)
ISSN (Print)2220-4806


19th International conference on New Interfaces for Musical Expression
Abbreviated titleNIME2019
CityPorto Alegre
Internet address


Dive into the research topics of 'Adaptive Mapping of Sound Collections for Data-driven Musical Interfaces'. Together they form a unique fingerprint.

Cite this